Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.7975. Min Act: -0.1700
Data Index: 2637556 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.7662. Min Act: -0.1700
Data Index: 3931709 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.7350. Min Act: -0.1700
Data Index: 4637097 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.7350. Min Act: -0.1700
Data Index: 5419792 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.7350. Min Act: -0.1700
Data Index: 3930186 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.7350. Min Act: -0.1700
Data Index: 2267608 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.7037. Min Act: -0.1700
Data Index: 5638029 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.6725. Min Act: -0.1700
Data Index: 4826689 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.6412. Min Act: -0.1700
Data Index: 6475860 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.6412. Min Act: -0.1700
Data Index: 3017496 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.6100. Min Act: -0.1700
Data Index: 4184012 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.6412. Min Act: -0.1700
Data Index: 1585162 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.6100. Min Act: -0.1700
Data Index: 689958 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.5475. Min Act: -0.1700
Data Index: 8811463 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.5162. Min Act: -0.1700
Data Index: 4067945 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.4850. Min Act: -0.1700
Data Index: 5454483 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.4850. Min Act: -0.1700
Data Index: 3715698 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.4537. Min Act: -0.1700
Data Index: 1373844 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.4850. Min Act: -0.1700
Data Index: 2650405 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7975. Min Range: -4.7975
Max Act: 4.4537. Min Act: -0.1700
Data Index: 2757039 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19